002f9879b2
Replaces cherry-picked upstream_ref with complete source trees. xllm/ — Iluvatar official C++ inference engine (15MB, 1470 files) Complete: kernels → layers → models → runtime → scheduler → api Excluded: .git, binary images, third_party submodule checkouts ds_vllm/ — Iluvatar official vllm fork (8MB, 703 files) Included: csrc/ (ALL CUDA kernels), fused_moe/, qwen3_5 model, _custom_ops Excluded: tests, benchmarks, docs, examples (not needed for reference) Critical call chains now fully traceable: MoE: moe_topk_softmax_kernels.cuh → ixformer.h → fused_moe.cpp → layer GDN: qwen3_gated_delta_net_base.cpp → qwen3_5_gated_delta_net.cpp Attention: ixformer.h → xllm_paged_attention → attention.cpp
15 lines
383 B
Plaintext
15 lines
383 B
Plaintext
include MANIFEST.in
|
|
include CMakeLists.txt
|
|
include LICENSE
|
|
include .gitmodules
|
|
recursive-include src *.*
|
|
recursive-include xllm *.py
|
|
recursive-include examples *.py
|
|
recursive-include third_party *
|
|
recursive-include docs *.*
|
|
recursive-include tools *.*
|
|
recursive-include scripts *.*
|
|
recursive-include proto *.*
|
|
prune */__pycache__
|
|
global-exclude *.o *.so *.dylib *.a .git *.pyc *.swp
|